| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006167129201356768, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006167129201356768, | |
| "grad_norm": 4.696722030639648, | |
| "learning_rate": 2e-05, | |
| "loss": 8.8509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006167129201356768, | |
| "eval_loss": 2.027782440185547, | |
| "eval_runtime": 32.7706, | |
| "eval_samples_per_second": 20.842, | |
| "eval_steps_per_second": 10.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012334258402713536, | |
| "grad_norm": 4.879605770111084, | |
| "learning_rate": 4e-05, | |
| "loss": 8.2884, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018501387604070306, | |
| "grad_norm": 4.912254810333252, | |
| "learning_rate": 6e-05, | |
| "loss": 8.9418, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018501387604070306, | |
| "eval_loss": 2.0177383422851562, | |
| "eval_runtime": 32.7619, | |
| "eval_samples_per_second": 20.847, | |
| "eval_steps_per_second": 10.439, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002466851680542707, | |
| "grad_norm": 5.2246294021606445, | |
| "learning_rate": 8e-05, | |
| "loss": 7.6679, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003083564600678384, | |
| "grad_norm": 5.750339508056641, | |
| "learning_rate": 0.0001, | |
| "loss": 8.0219, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0037002775208140612, | |
| "grad_norm": 7.092508316040039, | |
| "learning_rate": 0.00012, | |
| "loss": 7.126, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037002775208140612, | |
| "eval_loss": 1.6161603927612305, | |
| "eval_runtime": 32.8045, | |
| "eval_samples_per_second": 20.82, | |
| "eval_steps_per_second": 10.425, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004316990440949738, | |
| "grad_norm": 6.540224552154541, | |
| "learning_rate": 0.00014, | |
| "loss": 9.095, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004933703361085414, | |
| "grad_norm": 5.252821445465088, | |
| "learning_rate": 0.00016, | |
| "loss": 5.8836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005550416281221091, | |
| "grad_norm": 13.80943489074707, | |
| "learning_rate": 0.00018, | |
| "loss": 5.7512, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005550416281221091, | |
| "eval_loss": 1.355873942375183, | |
| "eval_runtime": 32.811, | |
| "eval_samples_per_second": 20.816, | |
| "eval_steps_per_second": 10.423, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006167129201356768, | |
| "grad_norm": 17.564971923828125, | |
| "learning_rate": 0.0002, | |
| "loss": 6.4214, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2160585604177920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |